Function Optimization via a Continuous Action-Set Reinforcement Learning Automata Model

摘要

Learning automata as a tool for machine learning, could search the optimal state adaptively in random environment. Function optimization is a fundamental issue and many practical models are ultimately the mathematical optimization problems. In this paper, we apply the basic continuous action-set reinforcement learning automata (CARLA) model to function optimization. An application model called equiCARLA is constructed by means of equidistant discretization and linear interpolation, and it presents a superiority over the existing algorithms not only in speed but also in precision. The experimental results demonstrate the effectiveness and efficiency of our model for function optimization.